广告合作
MCP.so
登录
S

Shopgraph MCP Server

@laundromatic

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

laundromatic

提交者

Krishna Brown

关于 Shopgraph MCP Server

AI shopping agents need structured product data to compare prices, check availability, and make decisions. Shopify Catalog covers Shopify merchants. Google UCP covers Google Shopping. ShopGraph covers everything else — the DTC brands, independent retailers, and niche suppliers th

#commerce#e-commerce#product-data#shopping#price-extraction#product-enrichment#schema-org#ai-agents#agentic-commerce#catalog#retail#dtc#open-web#structured-data#stripe-mpp

Shopgraph MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "shopgraph": {
      "type": "url",
      "url": "https://shopgraph.dev/mcp"
    }
  }
}

Shopgraph MCP Server 工具

4

Extract comprehensive product data from a URL including name, price, brand, images, availability, and more. Uses schema.org structured data when available, with LLM fallback. Costs $0.02 per call (cached results are free). Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.

Extract basic product attributes from a URL (name, price, brand, availability). Faster and cheaper than enrich_product. 50 free calls/month — no payment needed. Paid: $0.01 per call after free tier. Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.

Extract product data from raw HTML you already have (no HTTP fetch needed). Ideal when using Bright Data, Firecrawl, or any scraping API — pipe the HTML through ShopGraph for structured product data. Uses schema.org + LLM fallback. Costs $0.02 per call (cached results are free). Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.

Extract product data and return agent-readiness score (0-100). Scores structured data completeness, semantic richness, UCP compatibility, pricing clarity, and inventory signals. Full scoring breakdown included.

概览

What is Shopgraph?

Shopgraph is a Model Context Protocol server that extracts structured product data from URLs using Schema.org data and AI fallback, targeting agents that need product info from the open web where platform APIs are unavailable. It bills per API call via Stripe MPP.

How to use Shopgraph?

Install with npm install, set STRIPE_TEST_SECRET_KEY and GOOGLE_API_KEY in .env, then build and run via npm start (stdio) or npm run start:http (HTTP). Agents connect via MCP and call enrich_product or enrich_basic with a URL and optional payment_method_id.

Key features of Shopgraph

  • Schema.org extraction with 0.95 confidence
  • Gemini LLM fallback for pages without structured data
  • Pay-per-call billing via Stripe MPP
  • Cached results returned free (24‑hour TTL)
  • Playwright browser fallback for JS‑rendered or bot‑blocked pages
  • Two tools: enrich_product ($0.02) and enrich_basic ($0.01)

Use cases of Shopgraph

  • Gather product details from e‑commerce sites lacking public APIs
  • Enrich agent‑driven shopping comparisons with structured data
  • Extract basic product attributes (name, price, currency) for quick checks
  • Obtain reliable product data from pages that require JavaScript rendering

常见问题

1

How does Shopgraph handle payment?

Unauthenticated calls receive a 402 challenge with MPP payment details; authenticated calls with a `payment_method_id` are processed and billed per tool price.

2

What data extraction methods does Shopgraph use?

Primary extraction from Schema.org markup (0.95 confidence); if none found, Gemini LLM fallback (0.7+ confidence); Playwright browser fallback for bot‑blocked or JS‑rendered pages.

3

Are cached results free?

Yes, results returned from cache within the 24‑hour TTL are free of charge.

4

What runtime dependencies does Shopgraph require?

Node.js, with environment variables `STRIPE_TEST_SECRET_KEY` and `GOOGLE_API_KEY`; optionally, a Playwright browser for the JS‑rendering fallback.

5

Where does Shopgraph run?

The server can run via stdio (local MCP client) or HTTP (for Vercel/remote deployment). The MCP endpoint is `https://shopgraph.dev/mcp`.

评论

其他 分类下的更多 MCP 服务器

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K
广告合作